slices: | |
- sources: | |
- model: ../Hermes-3-Llama-3.1-70B | |
layer_range: [0, 21] # 21 | |
- model: ../L3.1-70B-Hanami-x1 | |
layer_range: [0, 21] | |
parameters: | |
t: 0.2 | |
- sources: | |
- model: ../L3.1-70B-Hanami-x1 | |
layer_range: [16, 36] # 20 | |
- model: ../Hermes-3-Llama-3.1-70B | |
layer_range: [16, 36] | |
parameters: | |
t: 0.8 | |
- sources: | |
- model: ../Hermes-3-Llama-3.1-70B | |
layer_range: [30, 50] # 20 | |
- model: ../L3.1-70B-Hanami-x1 | |
layer_range: [30, 50] | |
parameters: | |
t: 0.2 | |
- sources: | |
- model: ../L3.1-70B-Hanami-x1 | |
layer_range: [40, 64] # 24 | |
- model: ../Hermes-3-Llama-3.1-70B | |
layer_range: [40, 64] | |
parameters: | |
t: 0.8 | |
- sources: | |
- model: ../Hermes-3-Llama-3.1-70B | |
layer_range: [60, 80] # 20 | |
- model: ../L3.1-70B-Hanami-x1 | |
layer_range: [60, 80] | |
parameters: | |
t: 0.2 | |
merge_method: slerp | |
base_model: ../Hermes-3-Llama-3.1-70B | |
idtype: bfloat16 | |
tokenizer_source: ../Hermes-3-Llama-3.1-70B | |